TY - GEN
T1 - PPCSA
T2 - 35th International Conference on Advanced Information Networking and Applications, AINA 2021
AU - Moustafa, Ahmed
AU - Asad, Muhammad
AU - Shaukat, Saima
AU - Norta, Alexander
N1 - Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2021
Y1 - 2021
N2 - Federated Learning (FL) enables users devices (UDs) to collaboratively train a Deep Learning (DL) model on an individual’s gathered data, without revealing their privacy sensitive information to the centralized cloud server. Those UDs usually have limited data plans with a slow network connection to a centralized cloud server, which causes limited communication bandwidth between the contributing mobile users. To mitigate this problem, we propose a novel Partial Participation-based Compressed and Secure Aggregation (PPCSA) algorithm. To implement the PPCSA, we use a Sparse Compression Operator (SCO) that reduces the communication bits between the cloud server and the users while maintaining the FL requirements. In particular, PPCSA utilizes a novel compression method and introduces a Local Differential Privacy (LDP) based framework to achieve the communication-efficiency at a new level. Our experiments on a commonly used FL dataset show that PPCSA distinctively outperforms the state-of-the-art schemes in terms of convergence accuracy and communication bits.
AB - Federated Learning (FL) enables users devices (UDs) to collaboratively train a Deep Learning (DL) model on an individual’s gathered data, without revealing their privacy sensitive information to the centralized cloud server. Those UDs usually have limited data plans with a slow network connection to a centralized cloud server, which causes limited communication bandwidth between the contributing mobile users. To mitigate this problem, we propose a novel Partial Participation-based Compressed and Secure Aggregation (PPCSA) algorithm. To implement the PPCSA, we use a Sparse Compression Operator (SCO) that reduces the communication bits between the cloud server and the users while maintaining the FL requirements. In particular, PPCSA utilizes a novel compression method and introduces a Local Differential Privacy (LDP) based framework to achieve the communication-efficiency at a new level. Our experiments on a commonly used FL dataset show that PPCSA distinctively outperforms the state-of-the-art schemes in terms of convergence accuracy and communication bits.
UR - http://www.scopus.com/inward/record.url?scp=85105936632&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-75075-6_28
DO - 10.1007/978-3-030-75075-6_28
M3 - Conference proceedings published in a book
AN - SCOPUS:85105936632
SN - 9783030750749
T3 - Lecture Notes in Networks and Systems
SP - 345
EP - 357
BT - Advanced Information Networking and Applications - Proceedings of the 35th International Conference on Advanced Information Networking and Applications, AINA-2021
A2 - Barolli, Leonard
A2 - Woungang, Isaac
A2 - Enokido, Tomoya
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 12 May 2021 through 14 May 2021
ER -